diff options
| author | Hal Finkel <hfinkel@anl.gov> | 2016-03-28 17:52:08 +0000 |
|---|---|---|
| committer | Hal Finkel <hfinkel@anl.gov> | 2016-03-28 17:52:08 +0000 |
| commit | 7059d416228846346bdf2027be1fb0459f3f0ece (patch) | |
| tree | 9c9583359cbc6ef128738966b7aa30b375e4244e /llvm/test/CodeGen/PowerPC | |
| parent | b805f73ad1d75521f86cf2280837a0717f01b76b (diff) | |
| download | bcm5719-llvm-7059d416228846346bdf2027be1fb0459f3f0ece.tar.gz bcm5719-llvm-7059d416228846346bdf2027be1fb0459f3f0ece.zip | |
[PowerPC] On the A2, popcnt[dw] are very slow
The A2 cores support the popcntw/popcntd instructions, but they're microcoded,
and slower than our default software emulation. Specifically, popcnt[dw] take
approximately 74 cycles, whereas our software emulation takes only 24-28
cycles.
I've added a new target feature to indicate a slow popcnt[dw], instead of just
removing the existing target feature from the a2/a2q processor models, because:
1. This allows us to return more accurate information via the TTI interface
(I recognize that this currently makes no practical difference)
2. Is hopefully easier to understand (it allows the core's features to match
its manual while still having the desired effect).
llvm-svn: 264600
Diffstat (limited to 'llvm/test/CodeGen/PowerPC')
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/popcnt.ll | 22 |
1 files changed, 18 insertions, 4 deletions
diff --git a/llvm/test/CodeGen/PowerPC/popcnt.ll b/llvm/test/CodeGen/PowerPC/popcnt.ll index b304d72aede..79fc40e58a5 100644 --- a/llvm/test/CodeGen/PowerPC/popcnt.ll +++ b/llvm/test/CodeGen/PowerPC/popcnt.ll @@ -1,37 +1,51 @@ ; RUN: llc -march=ppc64 -mattr=+popcntd < %s | FileCheck %s +; RUN: llc -march=ppc64 -mcpu=pwr7 < %s | FileCheck %s +; RUN: llc -march=ppc64 -mcpu=a2q < %s | FileCheck %s --check-prefix=SLOWPC define i8 @cnt8(i8 %x) nounwind readnone { %cnt = tail call i8 @llvm.ctpop.i8(i8 %x) ret i8 %cnt -; CHECK: @cnt8 +; CHECK-LABEL: @cnt8 ; CHECK: rlwinm ; CHECK: popcntw ; CHECK: blr + +; SLOWPC-LABEL: @cnt8 +; SLOWPC-NOT: popcnt } define i16 @cnt16(i16 %x) nounwind readnone { %cnt = tail call i16 @llvm.ctpop.i16(i16 %x) ret i16 %cnt -; CHECK: @cnt16 +; CHECK-LABEL: @cnt16 ; CHECK: rlwinm ; CHECK: popcntw ; CHECK: blr + +; SLOWPC-LABEL: @cnt16 +; SLOWPC-NOT: popcnt } define i32 @cnt32(i32 %x) nounwind readnone { %cnt = tail call i32 @llvm.ctpop.i32(i32 %x) ret i32 %cnt -; CHECK: @cnt32 +; CHECK-LABEL: @cnt32 ; CHECK: popcntw ; CHECK: blr + +; SLOWPC-LABEL: @cnt32 +; SLOWPC-NOT: popcnt } define i64 @cnt64(i64 %x) nounwind readnone { %cnt = tail call i64 @llvm.ctpop.i64(i64 %x) ret i64 %cnt -; CHECK: @cnt64 +; CHECK-LABEL: @cnt64 ; CHECK: popcntd ; CHECK: blr + +; SLOWPC-LABEL: @cnt64 +; SLOWPC-NOT: popcnt } declare i8 @llvm.ctpop.i8(i8) nounwind readnone |
